Triple
T23121730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Mars-la-Tour |
E576910
|
entity |
| Predicate | objectiveFrance |
P15014
|
FINISHED |
| Object | withdraw Army of the Rhine toward Verdun |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: withdraw Army of the Rhine toward Verdun | Statement: [Battle of Mars-la-Tour, objectiveFrance, withdraw Army of the Rhine toward Verdun]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: objectiveFrance Context triple: [Battle of Mars-la-Tour, objectiveFrance, withdraw Army of the Rhine toward Verdun]
-
A.
objectiveOfFrance
chosen
Indicates that something is an objective, goal, or aim pursued by France.
-
B.
FrenchObjective
Indicates that an entity serves as the goal, target, or object of an action or relation specifically within a French linguistic or contextual framework.
-
C.
strengthFrance
Indicates a relationship where a level, measure, or attribute of strength is associated specifically with France.
-
D.
primaryFrenchDestination
Indicates that one entity is the main or most significant travel destination in France for another entity.
-
E.
resultForFrance
Indicates the outcome or result of an event, action, or process specifically as it pertains to France.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e50c500819095d59aef44388153 |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.